Loading

Content-Based Image Retrieval with Graph Theoretic Approach
Ali Broumandnia1, Mostafa Cheraghi2, Mohsen Azararjmand3

1Dr. Ali Broumandnia, Islamic Azad University, Science and Research Branch, Tehran, 14515/755, Iran.
2Mostafa Cheraghi, is with the Islamic Azad university-South Tehran Branch, Iran.
3Mohsen Azararjmand, Islamic Azad university-Qazvin Branch, Iran.
Manuscript received on January 12 2013. | Revised Manuscript Received on January 15 2013. | Manuscript published on January 25, 2013. | PP: 24-37 | Volume-1, Issue-3, January 2013. | Retrieval Number: C0128011313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The need for content-based image retrieval has increased with increment size and volume of digital images. This paper introduces the graph-based approach in order to retrieve the content-based image. In the proposed method, an image presents by a set of regions, while comparison of images are posing, each image represents by a graph, hence the estimation of the region correspondence transform into an graph matching problem. In addition, by using and image distance criteria, the difference between images obtained. Experimental results show that the proposed graph-theoretic image matching performance is acceptable.
Keywords: component: Content Based Image retrieval, Graph matching, Image segmentation, Matching Matrix.